Search Results for author: Seo Taek Kong

Found 3 papers, 0 papers with code

Relieving the Plateau: Active Semi-Supervised Learning for a Better Landscape

no code implementations8 Apr 2021 Seo Taek Kong, Soomin Jeon, Jaewon Lee, HongSeok Lee, Kyu-Hwan Jung

Equipped with a few theoretical insights, we propose convergence rate control (CRC), an AL algorithm that selects unlabeled data to improve the problem conditioning upon inclusion to the labeled set, by formulating an acquisition step in terms of improving training dynamics.

Active Learning

Better Optimization can Reduce Sample Complexity: Active Semi-Supervised Learning via Convergence Rate Control

no code implementations1 Jan 2021 Seo Taek Kong, Soomin Jeon, Jaewon Lee, Hong-Seok Lee, Kyu-Hwan Jung

We name this AL scheme convergence rate control (CRC), and our experiments show that a deep neural network trained using a combination of CRC and a recently proposed SSL algorithm can quickly achieve high performance using far less labeled samples than SL.

Active Learning

Almost Boltzmann Exploration

no code implementations25 Jan 2019 Harsh Gupta, Seo Taek Kong, R. Srikant, Weina Wang

In this paper, we show that a simple modification to Boltzmann exploration, motivated by a variation of the standard doubling trick, achieves $O(K\log^{1+\alpha} T)$ regret for a stochastic MAB problem with $K$ arms, where $\alpha>0$ is a parameter of the algorithm.

Multi-Armed Bandits

Cannot find the paper you are looking for? You can Submit a new open access paper.